Decentralizing Air Traffic Flow Management with Blockchain-based Reinforcement Learning

Ta Duong, Ketan Kumar Todi, Umang Chaudhary, Hong-Linh Truong

Abstract: We propose and implement a decentralized, intelligent air traffic flow management (ATFM) solution to improve the efficiency of air transportation in the ASEAN region as a whole. Our system, named BlockAgent, leverages the inherent synergy between multi-agent reinforcement learning (RL) for air traffic flow optimization; and the rising blockchain technology for a secure, transparent and decentralized coordination platform. As a result, BlockAgent does not require a centralized authority for effective ATFM operations. We have implemented several novel distributed coordination approaches for RL in BlockAgent. Empirical experiments with real air traffic data concerning regional airports have demonstrated the feasibility and effectiveness of our approach. To the best of our knowledge, this is the first work that considers blockchain-based, distributed RL for ATFM.